Difference between revisions of "Self-regulated Learning"
Jump to navigation
Jump to search
(added citation) |
m |
||
| Line 1: | Line 1: | ||
Zhang et al. (in press) https://www.upenn.edu/learninganalytics/ryanbaker/EDM22_paper_35.pdf] | Zhang et al. (in press) [https://www.upenn.edu/learninganalytics/ryanbaker/EDM22_paper_35.pdf] | ||
* Four detectors (i.e., numerical representation, contextual representation, outcome orientation, and data transformation) relating to two cognitive operations (assembling and translating) were built to detect middle school students' use of self-regulated learning in mathematical problem-solving process. | * Four detectors (i.e., numerical representation, contextual representation, outcome orientation, and data transformation) relating to two cognitive operations (assembling and translating) were built to detect middle school students' use of self-regulated learning in mathematical problem-solving process. | ||
* Detectors were built using XGBoost with labels coded from text replays and features distilled from log data and textual responses. | * Detectors were built using XGBoost with labels coded from text replays and features distilled from log data and textual responses. | ||
* In each detector, relatively small differences in AUC were observed across gender and racial/ethnic groups, and no student group (either gender or racial/ethnic group) consistently had the best-performing detectors | * In each detector, relatively small differences in AUC were observed across gender and racial/ethnic groups, and no student group (either gender or racial/ethnic group) consistently had the best-performing detectors | ||
Latest revision as of 05:15, 10 June 2022
Zhang et al. (in press) [1]
- Four detectors (i.e., numerical representation, contextual representation, outcome orientation, and data transformation) relating to two cognitive operations (assembling and translating) were built to detect middle school students' use of self-regulated learning in mathematical problem-solving process.
- Detectors were built using XGBoost with labels coded from text replays and features distilled from log data and textual responses.
- In each detector, relatively small differences in AUC were observed across gender and racial/ethnic groups, and no student group (either gender or racial/ethnic group) consistently had the best-performing detectors